Download as doc, pdf, or txt
Download as doc, pdf, or txt
You are on page 1of 3

Arthur C.

Aguilar Artificial Neural Networks


Quiz no. 1
1. Enumerate the 3 main components of a biological neuron and discuss how
this works (give the interrelationship).
ans. The three main components of a biological neuron are as follows:
a. Dendrites
b. oma
c. A!on
Neurons are highly specialized for the processing and transmission of cellular signals. Given the
diversity of functions performed by neurons in different parts of the nervous system, there is, as
expected, a wide variety in the shape, size, and electrochemical properties of neurons.
The dendrites of a neuron are cellular extensions with many branches, and metaphorically this
overall shape and structure is referred to as a dendritic tree. This is where the majority of input to
the neuron occurs. The soma is the central part of the neuron, he axon carries nerve
signals away from the soma (and also carries some types of information bac to it!. "any
neurons have only one axon, but this axon may#and usually will#undergo extensive branching,
enabling communication with many target cells. The part of the axon where it emerges from the
soma is called the axon hilloc.
2. What is a threshold neuron? Give its advantages and limitations.
ans. Threshold in a neuron is the point of depolarization at which the neuron fires, transmitting
information to another neuron. $sychologists use the concept of action potential threshold to
explain how neurons send information to each other. % neuron transmits information via electric
impulses sent through its axon. &hen a neuron is inactive, more positively charged ions lie
outside the axon membrane than within it. 'pon stimulation, the axon membrane admits more
sodium ions, rendering the neuron more positively charged. &hen the neuron reaches a certain
point of depolarization nown as the action potential threshold, it will fire( if it does not reach that
point, it will not fire. The action potential of a neuron is always the same.
). *valuate a +adamard,&alsh Transform (*-uation! on a .,/nput 01 2unction.
"# "$ "1 f
%
&
' ' ' ' (1
' ' 1 1 1
' 1 ' 1 1
' 1 1 1 1
1 ' ' 1 1
1 ' 1 1 1
1 1 ' 1 1
1 1 1 1 1
1 1 1 1 1 1 1 1 (1 )
(1 1 (1 1 (1 1 (1 1 1 $
(1 (1 1 1 (1 (1 1 1 1 $
1 (1 (1 1 1 (1 (1 1 1
(
$
(1 (1 (1 (1 1 1 1 1 ! 1 * $
1 (1 1 (1 (1 1 (1 1 1
(
$
1 1 (1 (1 (1 (1 1 1 1
(
$
(1 1 1 (1 1 (1 (1 1 1 $
f = 1/8 ( ! "#1!"#" $"#1#" !"#3 $ "#1#3 $"#"#3 !"#1#"#3)
". %ive the output of the e&pression'
(()1 3*+") = b()3 1*+")
where'
b = )1'"'1,+ 1'"'1,*
ans. Index exceeds matrix dimensions.
3. %ive an e-uivalent e&pression which results to the matri&'
# =
ans. X = [eye(3,3)];
X(3,2) = 1;
.. /rite a program which will produce a matri& (of an0 si1e) like the one shown.
ans. clear all
x = input(nter t!e num"er o# ro$s%);
y = input(nter t!e num"er o# columns%);
d = &eros(x,y);
d(1,1) = 1;
d(1,y) = 1;
d(x,y) = 1;
d(y,1) = 1;
d

You might also like